learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	1	12.2975	-0.0052	12.2975	3.5068
No log	2.0	2	10.9880	-0.0143	10.9880	3.3148
No log	3.0	3	9.6873	0.0018	9.6873	3.1124
No log	4.0	4	8.7021	0.0018	8.7021	2.9499
No log	5.0	5	7.7977	0.0018	7.7977	2.7924
No log	6.0	6	6.9293	0.0018	6.9293	2.6324
No log	7.0	7	6.3485	0.0018	6.3485	2.5196
No log	8.0	8	5.7148	0.0145	5.7148	2.3906
No log	9.0	9	4.9713	0.0157	4.9713	2.2296
No log	10.0	10	4.3743	0.0118	4.3743	2.0915
No log	11.0	11	3.8980	0.0040	3.8980	1.9743
No log	12.0	12	3.4355	0.0040	3.4355	1.8535
No log	13.0	13	3.0373	0.0040	3.0373	1.7428
No log	14.0	14	2.7164	0.0040	2.7164	1.6481
No log	15.0	15	2.4631	0.0384	2.4631	1.5694
No log	16.0	16	2.1382	0.1193	2.1382	1.4623
No log	17.0	17	1.9432	0.0705	1.9432	1.3940
No log	18.0	18	1.7528	0.0445	1.7528	1.3239
No log	19.0	19	1.5589	0.0445	1.5589	1.2486
No log	20.0	20	1.4372	0.0212	1.4372	1.1988
No log	21.0	21	1.2981	0.0212	1.2981	1.1393
No log	22.0	22	1.1716	0.0316	1.1716	1.0824
No log	23.0	23	1.0852	0.0316	1.0852	1.0417
No log	24.0	24	0.9990	0.0316	0.9990	0.9995
No log	25.0	25	0.9262	0.0316	0.9262	0.9624
No log	26.0	26	0.8739	0.0931	0.8739	0.9348
No log	27.0	27	0.8022	0.4153	0.8022	0.8957
No log	28.0	28	0.7516	0.4566	0.7516	0.8669
No log	29.0	29	0.7084	0.4313	0.7084	0.8417
No log	30.0	30	0.6715	0.4573	0.6715	0.8195
No log	31.0	31	0.6266	0.4601	0.6266	0.7916
No log	32.0	32	0.5921	0.4924	0.5921	0.7695
No log	33.0	33	0.5671	0.5415	0.5671	0.7531
No log	34.0	34	0.5430	0.5437	0.5430	0.7369
No log	35.0	35	0.5387	0.5171	0.5387	0.7340
No log	36.0	36	0.5162	0.5437	0.5162	0.7185
No log	37.0	37	0.5054	0.5596	0.5054	0.7109
No log	38.0	38	0.5253	0.5184	0.5253	0.7248
No log	39.0	39	0.5127	0.5428	0.5127	0.7160
No log	40.0	40	0.5130	0.5463	0.5130	0.7163
No log	41.0	41	0.4925	0.5626	0.4925	0.7018
No log	42.0	42	0.5237	0.5489	0.5237	0.7236
No log	43.0	43	0.4874	0.6119	0.4874	0.6981
No log	44.0	44	0.5021	0.6053	0.5021	0.7086
No log	45.0	45	0.5303	0.6013	0.5303	0.7282
No log	46.0	46	0.4881	0.6445	0.4881	0.6986
No log	47.0	47	0.5075	0.6171	0.5075	0.7124
No log	48.0	48	0.5172	0.6281	0.5172	0.7191
No log	49.0	49	0.5316	0.6149	0.5316	0.7291
No log	50.0	50	0.5254	0.6322	0.5254	0.7248
No log	51.0	51	0.5113	0.6433	0.5113	0.7151
No log	52.0	52	0.5525	0.6315	0.5525	0.7433
No log	53.0	53	0.5374	0.6318	0.5374	0.7331
No log	54.0	54	0.5208	0.6218	0.5208	0.7216
No log	55.0	55	0.5509	0.6216	0.5509	0.7422
No log	56.0	56	0.6223	0.6020	0.6223	0.7888
No log	57.0	57	0.5864	0.6148	0.5864	0.7658
No log	58.0	58	0.6566	0.5974	0.6566	0.8103
No log	59.0	59	0.6666	0.5999	0.6666	0.8165
No log	60.0	60	0.6140	0.6185	0.6140	0.7836
No log	61.0	61	0.6720	0.6238	0.6720	0.8198
No log	62.0	62	0.7548	0.5813	0.7548	0.8688
No log	63.0	63	0.7120	0.5955	0.7120	0.8438
No log	64.0	64	0.6034	0.6189	0.6034	0.7768
No log	65.0	65	0.6038	0.6219	0.6038	0.7770
No log	66.0	66	0.6969	0.5977	0.6969	0.8348
No log	67.0	67	0.7161	0.5909	0.7161	0.8462
No log	68.0	68	0.7600	0.5684	0.7600	0.8718
No log	69.0	69	0.8166	0.5668	0.8166	0.9037
No log	70.0	70	0.7503	0.5905	0.7503	0.8662
No log	71.0	71	0.6668	0.6199	0.6668	0.8166
No log	72.0	72	0.6755	0.6161	0.6755	0.8219
No log	73.0	73	0.7624	0.6090	0.7624	0.8732
No log	74.0	74	0.9403	0.5581	0.9403	0.9697
No log	75.0	75	1.0002	0.5347	1.0002	1.0001
No log	76.0	76	0.9454	0.5462	0.9454	0.9723

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold4

BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold4